|
Activity Number:
|
627
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 4, 2016 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
|
Abstract #318124
|
View Presentation
|
|
Title:
|
Multivariate Latent Structure in Bayesian Spatio-Temporal Health Models
|
|
Author(s):
|
Andrew B. Lawson*
|
|
Companies:
|
Medical University of South Carolina
|
|
Keywords:
|
Spatial ;
Bayesian ;
cancer ;
multivariate ;
temporal ;
health
|
|
Abstract:
|
Often geospatial disease outcomes can be profitably modelled together and their joint modeling leads to additional information concerning common etiology and shared confounding. With the addition of a temporal dimension this latent structural commonality can have time and space varying behavior. In addition there can be both joint and conditional dependence in the latent components. In this talk I focus on the possibility of the existence of temporal and spatial discrete latent models and also dynamic selection of models over space and time. An application to monitoring of lung and bronchus cancer and other respiratory cancers within counties of South Carolina over time is provided where both spatial and temporal dependency in model state is considered.
|
Authors who are presenting talks have a * after their name.
